TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation.
Xize ChengRongjie HuangLinjun LiZehan WangTao JinAoxiong YinFeiyang ChenXinyu DuanBaoxing HuaiZhou ZhaoPublished in: ACL (Findings) (2024)
Keyphrases
- visual speech
- text to speech
- hidden markov models
- audio visual speech recognition
- visual speech recognition
- speaker identification
- noisy environments
- audio signals
- machine translation
- video signals
- multi stream
- audio signal
- broadcast news
- speech signal
- acoustic features
- automatic speech recognition
- audio visual
- head motion
- multimedia
- video streams
- speech recognition
- face detection
- multiresolution